BerriAI/litellm · error · LangFlowError

flow_id is required; use model langflow/{flow_id}

Error message

flow_id is required; use model langflow/{flow_id}

What it means

LiteLLM requires the LangFlow flow ID in the model string. After disallowing parameter-based flow_id, _get_flow_id splits the model on '/' and strips whitespace; if the result is empty (model was 'langflow/', 'langflow/ ', or an empty string), it raises LangFlowError 400 telling you to use the 'langflow/{flow_id}' format.

Source

Thrown at litellm/llms/langflow/chat/transformation.py:82

    ) -> dict:
        return optional_params

    def _get_flow_id(self, model: str, optional_params: dict) -> str:
        """
        Extract flow_id from the authorized model name only.

        Model format: "langflow/{flow_id}". Request kwargs must not override
        flow_id (would allow calling another flow with the same API key).
        """
        if optional_params.get("flow_id") is not None:
            raise LangFlowError(
                status_code=400,
                message=("flow_id cannot be set via request parameters; use model langflow/{flow_id}"),
            )

        flow_id: Final = (model.split("/", 1)[1] if "/" in model else model).strip()
        if not flow_id:
            raise LangFlowError(
                status_code=400,
                message="flow_id is required; use model langflow/{flow_id}",
            )
        return flow_id

    def get_complete_url(
        self,
        api_base: str | None,
        api_key: str | None,
        model: str,
        optional_params: dict,
        litellm_params: dict,
        stream: bool | None = None,
    ) -> str:
        if api_base is None:
            raise ValueError(
                "api_base is required for LangFlow. Set it via LANGFLOW_API_BASE env var or api_base parameter."
            )

View on GitHub (pinned to 6c2dcb801b)

Solutions

  1. Set the model to the full form including the flow ID: "langflow/<your-flow-id>"
  2. If the model comes from a template/config, make sure the interpolated variable is non-empty and stripped
  3. Fetch valid flow IDs from the LangFlow UI URL or /api/v1/flows and use one

Example fix

# before
litellm.completion(model="langflow/", messages=msgs)

# after
litellm.completion(model="langflow/8b0e04bc-4f28-4ed9-9c1c-1d6c2ece7d33", messages=msgs)
Defensive patterns

Strategy: validation

Validate before calling

def resolve_langflow_model(flow_id: str | None) -> str:
    if not flow_id or not flow_id.strip():
        raise ValueError("flow_id is required and must be a non-empty string")
    return f"langflow/{flow_id.strip()}"

Type guard

def is_nonempty_flow_id(v) -> bool:
    return isinstance(v, str) and bool(v.strip())

Try / catch

try:
    litellm.completion(model=resolve_langflow_model(cfg["flow_id"]), messages=msgs)
except LangFlowError as e:
    if e.status_code == 400:
        # surface a config error: the model string did not carry a flow id
        raise RuntimeError("LangFlow model misconfigured: missing flow id") from e

Prevention

When it happens

Trigger: model="langflow/" or "langflow/ " (empty segment after the slash); model=""; a model alias/config whose name resolves to a bare provider prefix without a flow ID; whitespace-only flow ID from a misformatted config string.

Common situations: Router/model_list entry with model_name="langflow/" awaiting a value; templating bug that interpolates an empty variable into the model string (f"langflow/{flow_id}" with flow_id=None or ''); copying a config example and forgetting to substitute the flow ID.

Related errors

AI-assisted analysis of BerriAI/litellm@6c2dcb801b (2026-08-15). Data as JSON: /api/errors/30e280fe9c674a20. Report an issue: GitHub.